[Common] Update NCCL submodule to have the fix for MAX_SUPPORTED_TOKENS_PER_RANK (#3150)

* nccl with relax num_dispatch_tokens%64!=0

Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>

* Skip EP tests/examples on nodes without NVLink

Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>

---------

Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>

Author: phu0ngng

3rdparty/nccl

@@ -47,6 +47,13 @@ NUM_GPUS=$(nvidia-smi -L 2>/dev/null | wc -l)
 if [ "${NUM_GPUS}" -lt 4 ]; then
   echo "EP bench requires >=4 GPUs (found ${NUM_GPUS}); SKIPPING."; exit 0
 fi
+
+# NCCL EP requires active NVLink P2P among ranks on the node.
+if ! nvidia-smi nvlink --status 2>/dev/null | grep -qE 'Link [0-9]+:.*GB/s'; then
+  echo "NVLink not detected on this platform — EP bench requires NVLink; SKIPPING."
+  exit 0
+fi
+
 NUM=4
 COORD="${COORD:-127.0.0.1:23457}"
 TIMEOUT_S="${TIMEOUT_S:-1800}"

examples/jax/ep/bench/run_ep_bench.sh

@@ -35,6 +35,12 @@ if (( MIN_SM > 0 && MIN_SM < 90 )); then
     exit 0
 fi
 
+# NCCL EP requires active NVLink P2P among ranks on the node.
+if ! nvidia-smi nvlink --status 2>/dev/null | grep -qE 'Link [0-9]+:.*GB/s'; then
+    echo "NVLink not detected on this platform; SKIPPING."
+    exit 0
+fi
+
 TEST_BIN="${BUILD_DIR}/test_ep"
 if [[ ! -x "${TEST_BIN}" ]]; then
     echo "ERROR: binary not found: ${TEST_BIN}"

tests/cpp_distributed/run_test_ep.sh

@@ -32,6 +32,13 @@ if [ "${NUM_RUNS}" -lt 4 ]; then
   echo "NCCL EP requires at least 4 GPUs (found ${NUM_RUNS}); SKIPPING."
   exit 0
 fi
+
+# NCCL EP requires active NVLink P2P among ranks on the node.
+if ! nvidia-smi nvlink --status 2>/dev/null | grep -qE 'Link [0-9]+:.*GB/s'; then
+  echo "NVLink not detected on this platform — EP test requires NVLink; SKIPPING."
+  exit 0
+fi
+
 # Default test mesh is (2, 2); use exactly 4 ranks even on larger boxes.
 NUM_RUNS="${NVTE_TEST_EP_NUM_RANKS:-4}"
 

tests/jax/multi_process_launch_ep.sh

@@ -18,10 +18,10 @@ if [ "${DETECTED_GPUS}" -lt 4 ]; then
   exit 0
 fi
 
-# NCCL EP requires NVLink/NVSwitch between GPUs.
+# NCCL EP requires active NVLink P2P among ranks on the node.
 # On PCIe-only nodes (no NVLink) it falls back to the network
 # transport and deadlocks, so skip cleanly there.
-if ! nvidia-smi topo -m 2>/dev/null | grep -qE "\bNV[0-9]+\b"; then
+if ! nvidia-smi nvlink --status 2>/dev/null | grep -qE 'Link [0-9]+:.*GB/s'; then
   echo "No NVLink between GPUs (PCIe-only fabric); NCCL EP is unsupported here. SKIPPING."
   exit 0
 fi